vacancy/SceneGraphParser
A python toolkit for parsing captions (in natural language) into scene graphs (as symbolic representations).
When you have a natural language sentence describing a scene, this tool helps you automatically break it down into a structured 'scene graph'. It takes your text descriptions as input and outputs a clear list of objects (like 'woman' or 'piano') and the relationships between them (like 'woman playing piano'). This is useful for researchers and developers working on projects that need to understand visual content from text.
592 stars. No commits in the last 6 months.
Use this if you need to extract structured data about objects and their interactions from descriptive sentences, especially for tasks involving image or video analysis.
Not ideal if you're looking for a tool to analyze complex sentiment, generate text, or perform general-purpose natural language understanding beyond scene description.
Stars
592
Forks
55
Language
Python
License
MIT
Category
Last pushed
Jan 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/vacancy/SceneGraphParser"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ntrang086/image_captioning
generate captions for images using a CNN-RNN model that is trained on the Microsoft Common...
fregu856/CS224n_project
Neural Image Captioning in TensorFlow.
ltguo19/VSUA-Captioning
Code for "Aligning Linguistic Words and Visual Semantic Units for Image Captioning", ACM MM 2019
Abdelrhman-Yasser/video-content-description
Video content description model for generating descriptions for unconstrained videos
kozodoi/BMS_Molecular_Translation
Image-to-text translation of chemical molecule structures with deep learning (top-5% Kaggle solution)